Regional energy hosting collaborative management system and method based on cloud platform

Abstract

The invention discloses a regional energy hosting collaborative management system and method based on a cloud platform, and relates to the technical field of data analysis. The system comprises a regional grid division and correlation analysis module, a data verification and feature extraction module, a load prediction and collaborative potential analysis module and a scheduling path optimization and instruction execution module. The regional grid division and association analysis module collects geographical and energy node information by means of a cloud platform, divides regional unit grids and constructs an energy flow association graph; the data verification and feature extraction module verifies and screens multi-energy historical data, calculates conversion efficiency and constructs a coupling feature matrix; the load prediction and collaborative potential analysis module predicts a multi-energy load, searches a surplus grid, evaluates collaborative potential and generates a supply and demand gap matrix; and the scheduling path optimization and instruction execution module screens an optimal scheduling path, sends an instruction to the energy equipment and updates the association diagram.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, in particular to a cloud platform-based regional energy hosting collaborative management system and method. BACKGROUND

[0002] With the continuous growth of global energy demand and the increasing severity of environmental problems, how to achieve efficient and clean energy management has become a key research topic for governments and scientific research institutions. Regional energy hosting collaborative management system, as a management method integrating multiple energy forms, can achieve optimal scheduling and resource sharing, and gradually becomes an important tool in regional energy management. This system comprehensively manages the whole process of energy production, transmission, distribution and consumption through intelligent monitoring, data analysis and collaborative optimization, aiming to improve energy utilization efficiency, reduce costs and promote sustainable development.

[0003] However, current energy scheduling research mostly focuses on the optimal management of single energy systems, such as power grid scheduling or gas pipeline network scheduling. This localized management mode often leads to low energy utilization efficiency, with some energy surplus and others facing shortages, resulting in resource waste. In addition, existing regional energy management systems usually rely on static scheduling strategies, lacking real-time analysis and collaborative scheduling of multiple energy forms. Traditional management methods cannot dynamically adjust energy combinations according to real-time demand and supply changes, resulting in suboptimal energy utilization efficiency. SUMMARY

[0004] The purpose of the present application is to provide a cloud platform-based regional energy hosting collaborative management system and method to solve the problems raised in the background.

[0005] In order to solve the above technical problems, the present application provides the following technical solutions:

[0006] The cloud platform-based regional energy hosting collaborative management method comprises the following steps:

[0007] Step S100. Collecting geographic information data and energy node information of the target region using the cloud platform, dividing the target region according to the geographic information data and energy node information, thereby obtaining a plurality of regional unit grids; obtaining the energy node topology structure of the target region, thereby constructing a cross-grid energy flow correlation graph;

[0008] Step S200. Obtaining multi-energy historical data of each regional unit grid, combining the energy flow correlation graph to perform data rationality verification on the multi-energy historical data, and filtering the multi-energy historical data according to the verification result; according to the energy flow correlation graph, combining the filtered multi-energy historical data, calculating the cross-grid energy conversion efficiency, and extracting the time correlation characteristics, thereby constructing a coupling feature matrix;

[0009] Step S300. According to the energy flow correlation diagram and the coupling feature matrix, the multi-energy load of each regional unit grid is predicted; based on the energy flow correlation diagram, the energy surplus grid is searched and the cross-energy conversion feasibility is evaluated, so as to perform the synergy potential analysis; according to the prediction result and the synergy potential analysis result, the energy supply and demand gap of each regional unit grid is calculated, and the supply and demand gap matrix is generated;

[0010] Step S400. Based on the energy flow correlation diagram, the optimal scheduling path matched with the energy surplus grid is screened out from the energy shortage grid in combination with the supply and demand gap matrix; according to the optimal scheduling path, the scheduling instruction is sent to the corresponding energy equipment, and the energy flow correlation diagram is updated synchronously.

[0011] Further, step S100 comprises:

[0012] S101. Collecting geographical information data and energy node information of a target region by using a cloud platform, wherein the target region is a spatial range of energy hosting and collaborative management, and the energy node is a physical entity with energy production, storage, conversion or consumption function in the target region; according to the geographical information data and the energy node information, the area A_total of the target region and the distribution position of the energy node are obtained, the target region is equally divided into N_grid regional unit grids according to a preset regional unit grid area A_grid, and N_grid=A_total / A_grid, and the divided regional unit grids are marked with unique numbers g(m,n), wherein m∈[1,M], n∈[1,N], m represents the row number of the regional unit grid, n represents the column of the regional unit grid, M represents the horizontal grid number of the regional unit grid, and N represents the vertical grid number of the regional unit grid; and the geometric range of each regional unit grid is: the horizontal coordinate interval x∈[x_min+(m-1)·l_grid, x_min+m·l_grid], and the vertical coordinate interval y∈[y_min+(m-1)·l_grid, y_min+m·l_grid], wherein l_grid represents the side length of the regional unit grid, and the regional unit grid is a square; for any energy node i, the corresponding coordinates are represented as (xi, yi), and the corresponding grid number is: And mi∈[1,M], ni∈[1,N], thereby forming a mapping relationship between the energy node i and the corresponding regional unit grid number g(mi,ni);

[0013] S102. Obtain the energy node topology structure of the target region, to obtain the mutual relationship between the energy nodes in the target region, thereby constructing the cross-grid energy flow correlation graph G=(V, E), wherein V represents the energy node set of the target region, E represents the edge set of the energy nodes of the target region, and the edge eij represents the energy transmission path of the edge node i to j.

[0014] Further, step S200 comprises:

[0015] S201. Obtain the multi-energy historical data of each regional unit grid, wherein the multi-energy historical data comprises the production, storage and consumption data of electricity, heat and gas; perform data alignment and standardization on the multi-energy historical data of each regional unit grid, and arrange into a time sequence D g(m,n) (t), wherein t represents time, D g(m,n) (t) represents the multi-energy historical data of the regional unit grid g(m, n) at time t, and D g(m,n) (t) = [P prod (m, n, t), S stor (m, n, t), E cons (m, n, t)], wherein P prod (m, n, t) represents the production data of the regional unit grid g(m, n) at time t, S stor (m, n, t) represents the storage data of the regional unit grid g(m, n) at time t, and E cons (m, n, t) represents the consumption data of the regional unit grid g(m, n) at time t; based on the energy flow correlation graph, for any edge eij ∈ E, for the energy node i ∈ g(m1, n1) and the energy node j ∈ g(m2, n2), the corresponding cross-grid transmission amount P trans (i→j, t) needs to satisfy the constraint condition: P trans (i→j, t) ≤ Cap(eij), and P trans (i→j, t) ≤ [P prod (m1, n1, t) + S stor_out (m1, n1, t)] - E cons (m1, n1, t)], wherein Cap(eij) represents the rated capacity of the transmission path from the energy node i to the energy node j, and S stor_out represents the output amount of the storage device of the regional unit grid; for each regional unit grid g(m, n), the energy conservation within the grid needs to be satisfied, and the formula is:

[0016] P prod (m, n, t) + ∑ in P trans (→g, t) + S stor_out (m, n, t) = E cons(m, n, t) +∑ out P trans (g→, t) + S stor_in

[0017] (m, n, t) + Δ loss (m, n, t), where∑ in P trans (→g, t) represents the total energy transmitted from other regional unit grids to the current regional unit grid,∑ out P trans (g→, t) represents the total energy transmitted from the current regional unit grid to other regional unit grids; S stor_in (m, n, t) represents the input of the storage device of the current regional unit grid; Δ loss (m, n, t) represents the energy loss within the current regional unit grid; the multiple energy historical data satisfying the constraint condition and the energy conservation within the grid are screened, thereby forming the historical effective data D valid_g(m,n) (t).

[0018] S202. Based on the transmission path eij existing in the energy flow correlation diagram, in combination with the effective data D valid_g(m,n) (t), the energy instantaneous conversion efficiency η trans (i→j, t) is calculated, and η trans (i→j, t) = [P recv (j, t) / P trans (i→j, t)] × 100%, where P recv (j, t) represents the actual received energy of the energy node j; according to the energy instantaneous conversion efficiency η trans (i→j, t), the average value within the corresponding time window is calculated, thereby obtaining the cross-grid average conversion efficiency ημ trans (i→j); based on the historical effective data D valid_g(m,n) (t) of each regional unit grid, the corresponding time correlation features are extracted therefrom, for any two regional unit grids g(m1, n1) and regional unit grids g(m2, n2), the Pearson correlation coefficient is used to calculate the correlation coefficient ρ(g1, g2) of the corresponding time correlation features, and the time correlation features with the correlation coefficient ρ(g1, g2) greater than the threshold value ρ0 are screened; according to the cross-grid average conversion efficiency ημ trans (i→j) and the correlation coefficient ρ(g1, g2) of the screened time correlation features, the comprehensive evaluation index C(g1, g2) = w1 × ρ(g1, g2) + w2 × ημ trans(i→j), where w1 and w2 represent weight factors, and w1+w2=1; the comprehensive evaluation indicators of all regional unit grids are summarized, and the coupling characteristic matrix C is constructed according to the numbering order of the regional unit grids, and the diagonal elements in the coupling characteristic matrix C are 1.

[0019] Furthermore, step S300 includes:

[0020] S301. For each regional unit grid g(m,n), according to the corresponding historical valid data D valid_g(m,n) (t) and the coupling feature matrix C, the trained time series model is used to predict the multi-energy load of each regional unit grid. The corresponding prediction formula is: D' (m,n) (t+1)=f(D valid_g(m,n) (t)), where D' (m,n) (t+1) represents the multi-energy predicted load at the next time point, and f() represents the prediction function obtained by the time series model. The multi-energy predicted load of each regional unit grid is obtained, and the net energy output ΔE(m,n,t) during the prediction period is calculated using the following formula:

[0021] ΔE(m,n,t)=P' prod (m,n,t)+S' stor_out (m,n,t)]-E' cons (m,n,t); Based on the net energy output ΔE(m,n,t) during the forecast period, the surplus grid set H1 and the shortage grid set H2 are obtained, where the surplus grid set H1 = {g(m,n)|ΔE(m,n,t)>E1} and the shortage grid set H2 = {g(m,n)|ΔE(m,n,t)<-E2}, where E1 and E2 represent preset thresholds, which are set according to the energy supply and demand fluctuation characteristics of the target area;

[0022] S302. Analyze surplus grid g based on energy flow correlation diagram h1 ∈H1 and the shortage grid g h2 ∈H2 transmission path eij, evaluate the feasibility of the energy conversion path, and define the corresponding evaluation index F(g h1 ,g h2 ), if the surplus grid g h1 and shortage grid g h2 There is a transmission path eij∈E and η trans (g h1 →g h2 )≥η min , then the evaluation index F(g h1 ,g h2 )=1; otherwise, the evaluation index F(g h1 ,g h2) = 0; where η trans (g h1 → g h2 ) represents the average energy conversion efficiency from surplus grid to shortage grid g h2 , η min is the preset minimum efficiency threshold; according to the prediction result and the evaluation result of the cross-energy conversion feasibility, a synergy potential matrix T is constructed, and the corresponding element is defined as T(g h1 , g h2 ) = F(g h1 , g h2 ) * min(ΔE(g h1 ), |ΔE(g h2 )|) * η trans (g h1 → g h2 );

[0023] S303. For each regional unit grid g(m, n), an initial gap Q0(m, n) not considering synergy is calculated, and Q0(m, n) = E' cons (m, n) - [P' prod (m, n, t) + S' stor_out (m, n, t)], wherein Q0(m, n) greater than 0 represents shortage, and Q0(m, n) less than 0 represents surplus; based on the synergy potential matrix T, surplus is distributed according to the greedy algorithm: Q(m, n) = Q0(m, n) - å gh1∈H1 α(g h1 , m, n) * T(g h1 , m, n), wherein α(g h1 , m, n) represents a distribution coefficient, the value range is [0, 1], and å gh1∈H1 α(g h1 , m, n) is less than or equal to 1; when Q(m, n) > 0, it represents the energy shortage amount still existing after the synergy scheduling; when Q(m, n) < 0, it represents the energy surplus amount remaining after the synergy scheduling; when Q(m, n) = 0, it represents that the energy supply and demand are completely balanced; all regional unit grids with Q(m, n) > 0 are summarized as the final supply and demand gap, and are arranged in order according to the row number m and the column number n of the grid number, to construct a supply and demand gap matrix Q.

[0024] Further, step S400 comprises:

[0025] S401. Based on the energy flow correlation graph and the supply and demand gap matrix Q, for each shortage grid g h2 , search all feasible transmission paths of surplus grid g h1 , and the corresponding path feasibility constraint condition is: transmission path eij E, and P trans (i→j, t) ≤ Cap(eij); surplus grid gh1 The dispatchable amount of g sched (g h1 ,t)≤∣Q(g h1 )∣·β(g h1 ,g h2 ), wherein β(g h1 ,g h2 ) represents an allocation coefficient, the demand amount of the short grid g h2 needs to satisfy P recv (g h2 ,t)≤Q(g h2 ), the path comprehensive score S(e ij ) is defined, and S(eij)=w3·η trans (i→j)-w4·ΔL(e ij ), wherein η trans (i→j) represents the average conversion efficiency of the path, ΔL(e ij ) represents the path transmission loss, w3 and w4 represent weight factors, and w3+w4=1; the candidate dispatch paths are arranged in descending order according to the path comprehensive score S(e ij ), thereby obtaining the candidate dispatch paths.

[0026] S402. For each short grid, the candidate dispatch path with the conversion efficiency (g h1 →g h2 )≥η min is preferentially matched; if there are multiple candidate dispatch paths, the candidate dispatch path with the maximum path comprehensive score S(e ij ) is selected as the optimal dispatch path matched, and it is ensured that the remaining amount of the surplus grid Q(g h1 )-P sched (g h1 ,t)≥0, and the demand amount of the short grid Q(g h2 )-P recv (g h2 ,t)≤0; the optimal dispatch paths of all short grids are summarized to generate the dispatch instruction for the energy equipment, and the energy flow correlation graph is synchronously updated according to the actual dispatch result.

[0027] The regional energy hosting collaborative management system based on the cloud platform comprises a regional grid division and correlation analysis module, a data verification and feature extraction module, a load prediction and collaborative potential analysis module, and a dispatch path optimization and instruction execution module.

[0028] The regional grid division and correlation analysis module collects geographic information data and energy node information of a target region by using a cloud platform, divides the target region according to the geographic information data and the energy node information, and thus obtains a plurality of regional unit grids; acquires a topology structure of energy nodes of the target region, and thus constructs an energy flow correlation graph across the grids;

[0029] The data verification and feature extraction module acquires multi-energy historical data of each regional unit grid, performs data rationality verification on the multi-energy historical data in combination with the energy flow correlation graph, and filters the multi-energy historical data according to the verification result; calculates a cross-grid energy conversion efficiency according to the energy flow correlation graph in combination with the filtered multi-energy historical data, and extracts time correlation features, and thus constructs a coupling feature matrix;

[0030] The load prediction and coordination potential analysis module predicts multi-energy loads of each regional unit grid according to the energy flow correlation graph and the coupling feature matrix; searches for energy surplus grids and evaluates cross-energy conversion feasibility based on the energy flow correlation graph, and thus performs coordination potential analysis; calculates energy supply-demand gaps of each regional unit grid according to the prediction result and the coordination potential analysis result, and generates a supply-demand gap matrix;

[0031] The dispatching path optimization and instruction execution module filters an optimal dispatching path matched with an energy shortage grid from the energy surplus grid based on the energy flow correlation graph in combination with the supply-demand gap matrix; sends a dispatching instruction to a corresponding energy device according to the optimal dispatching path, and synchronously updates the energy flow correlation graph.

[0032] Further, the regional grid division and correlation analysis module comprises a grid division unit and a correlation graph construction unit.

[0033] The grid division unit collects geographic information data and energy node information of a target region by using a cloud platform, divides the target region according to the geographic information data and the energy node information, and thus obtains a plurality of regional unit grids; the correlation graph construction unit acquires a topology structure of energy nodes of the target region, and thus constructs an energy flow correlation graph across the grids.

[0034] Further, the data verification and feature extraction module comprises a data verification and filtering unit and a coupling feature extraction unit.

[0035] The data verification and filtering unit acquires multi-energy historical data of each regional unit grid, performs data rationality verification on the multi-energy historical data in combination with the energy flow correlation graph, and filters the multi-energy historical data according to the verification result; the coupling feature extraction unit calculates a cross-grid energy conversion efficiency according to the energy flow correlation graph in combination with the filtered multi-energy historical data, and extracts time correlation features, and thus constructs a coupling feature matrix.

[0036] Further, the load prediction and collaborative potential analysis module comprises a multi-energy load prediction unit and a collaborative potential evaluation and gap calculation unit;

[0037] The multi-energy load prediction unit predicts the multi-energy load of each regional unit grid according to the energy flow correlation graph and the coupling characteristic matrix; the collaborative potential evaluation and gap calculation unit searches for energy surplus grids and evaluates the cross-energy conversion feasibility based on the energy flow correlation graph, thereby performing collaborative potential analysis; according to the prediction result and the collaborative potential analysis result, the energy supply and demand gap of each regional unit grid is calculated, and a supply and demand gap matrix is generated.

[0038] Further, the dispatching path optimization and instruction execution module comprises an optimal dispatching path screening unit and a dispatching instruction generation and correlation graph updating unit;

[0039] The optimal dispatching path screening unit screens out the optimal dispatching path matched with the energy shortage grid from the energy surplus grid based on the energy flow correlation graph in combination with the supply and demand gap matrix; the dispatching instruction generation and correlation graph updating unit sends a dispatching instruction to the corresponding energy device according to the optimal dispatching path, and synchronously updates the energy flow correlation graph.

[0040] Compared with the prior art, the beneficial effects of the present application are: the present application realizes the collaborative management of the multi-energy system by combining multiple energy forms such as electricity, heat and gas, and can dynamically adjust according to the actual demand and supply conditions, thereby effectively avoiding the problems of excess and shortage in a single energy system. The present application collects geographic information data and energy node information within the region through the cloud platform, combines real-time data analysis, and realizes intelligent scheduling and optimized management of the regional energy system; the application of the cloud platform not only improves the data processing capability, but also enables the energy scheduling to realize more flexible and real-time adjustment. The present application accurately predicts the multi-energy load of the regional unit grid through multiple means such as rationality verification of historical data, calculation of energy conversion efficiency and collaborative potential analysis, and performs collaborative scheduling based on energy surplus and shortage; this method not only improves the energy utilization efficiency, but also can adjust the energy flow path in real time according to the supply and demand gap of different regions, avoiding resource waste. The present application innovatively introduces the coupling characteristic matrix and collaborative potential analysis, constructs a more accurate collaborative scheduling model based on the energy flow correlation graph and time correlation characteristics across grids, and can accurately identify the energy supply and demand gap of each region, and maximize the energy utilization efficiency through optimal path scheduling. In the scheduling process, the present application preferentially selects the optimal dispatching path through path comprehensive scoring, to minimize the total transmission loss and maximize the energy conversion efficiency, ensuring that the energy flow in the scheduling process is more efficient. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings are included to provide a further understanding of the application, and are incorporated in and constitute a part of the specification, illustrate embodiments of the application, and are used to explain the present application, but are not intended to limit the present application. In the drawings:

[0042] Figure 1 is a schematic diagram of the cloud platform-based regional energy hosting collaborative management system of the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0044] Please refer to Figure 1 The present application provides technical solutions:

[0045] The cloud platform-based regional energy hosting collaborative management system comprises a regional grid division and correlation analysis module, a data verification and feature extraction module, a load prediction and collaborative potential analysis module, and a dispatching path optimization and instruction execution module.

[0046] The regional grid division and correlation analysis module collects geographic information data and energy node information of a target region by using a cloud platform, divides the target region according to the geographic information data and the energy node information, thereby obtaining a plurality of regional unit grids, and acquires a topology structure of energy nodes of the target region, thereby constructing a cross-grid energy flow correlation graph.

[0047] The data verification and feature extraction module acquires multi-energy historical data of each regional unit grid, performs data rationality verification on the multi-energy historical data in combination with the energy flow correlation graph, and performs screening on the multi-energy historical data according to the verification result; calculates cross-grid energy conversion efficiency according to the energy flow correlation graph in combination with the screened multi-energy historical data, and extracts time correlation features, thereby constructing a coupling feature matrix.

[0048] The load prediction and collaborative potential analysis module predicts multi-energy load of each regional unit grid according to the energy flow correlation graph and the coupling feature matrix; searches for energy surplus grids and evaluates cross-energy conversion feasibility based on the energy flow correlation graph, thereby performing collaborative potential analysis; calculates energy supply-demand gaps of each regional unit grid according to the prediction result and the collaborative potential analysis result, and generates a supply-demand gap matrix.

[0049] The scheduling path optimization and instruction execution module screens the optimal scheduling path matched with the energy shortage grid from the energy surplus grid based on the energy flow correlation graph in combination with the supply-demand gap matrix; according to the optimal scheduling path, the scheduling instruction is sent to the corresponding energy equipment, and the energy flow correlation graph is updated synchronously.

[0050] The regional grid division and correlation analysis module comprises a grid division unit and a correlation graph construction unit;

[0051] The grid division unit collects geographic information data and energy node information of the target region by using the cloud platform, divides the target region according to the geographic information data and the energy node information, and thus obtains a plurality of regional unit grids; the correlation graph construction unit obtains the energy node topology structure of the target region, and thus constructs the cross-grid energy flow correlation graph.

[0052] The data verification and feature extraction module comprises a data verification and screening unit and a coupled feature extraction unit;

[0053] The data verification and screening unit obtains the multi-energy historical data of each regional unit grid, performs data rationality verification on the multi-energy historical data in combination with the energy flow correlation graph, and screens the multi-energy historical data according to the verification result; the coupled feature extraction unit calculates the cross-grid energy conversion efficiency according to the energy flow correlation graph in combination with the screened multi-energy historical data, and extracts the time correlation feature, and thus constructs the coupled feature matrix.

[0054] The load prediction and collaborative potential analysis module comprises a multi-energy load prediction unit and a collaborative potential evaluation and gap calculation unit;

[0055] The multi-energy load prediction unit predicts the multi-energy load of each regional unit grid according to the energy flow correlation graph and the coupled feature matrix; the collaborative potential evaluation and gap calculation unit searches for the energy surplus grid and evaluates the cross-energy conversion feasibility based on the energy flow correlation graph, and thus performs the collaborative potential analysis; according to the prediction result and the collaborative potential analysis result, the energy supply-demand gap of each regional unit grid is calculated, and the supply-demand gap matrix is generated.

[0056] The scheduling path optimization and instruction execution module comprises an optimal scheduling path screening unit and a scheduling instruction generation and correlation graph updating unit;

[0057] The optimal scheduling path screening unit screens the optimal scheduling path matched with the energy shortage grid from the energy surplus grid based on the energy flow correlation graph in combination with the supply-demand gap matrix; the scheduling instruction generation and correlation graph updating unit sends the scheduling instruction to the corresponding energy equipment according to the optimal scheduling path, and updates the energy flow correlation graph synchronously.

[0058] The cloud platform-based regional energy hosting collaborative management method comprises the following steps:

[0059] Step S100. Collect geographical information data and energy node information of the target area by using the cloud platform, divide the target area according to the geographical information data and the energy node information, thereby obtaining a plurality of regional unit grids; obtain the energy node topology structure of the target area, thereby constructing a cross-grid energy flow correlation graph;

[0060] Step S200. Obtain the multi-energy historical data of each regional unit grid, perform data rationality verification on the multi-energy historical data in combination with the energy flow correlation graph, and perform screening on the multi-energy historical data according to the verification result; calculate the cross-grid energy conversion efficiency according to the energy flow correlation graph in combination with the screened multi-energy historical data, and extract time correlation characteristics, thereby constructing a coupling feature matrix;

[0061] Step S300. Predict the multi-energy load of each regional unit grid according to the energy flow correlation graph and the coupling feature matrix; search for energy surplus grids and evaluate the cross-energy conversion feasibility based on the energy flow correlation graph, thereby performing collaborative potential analysis; calculate the energy supply and demand gap of each regional unit grid according to the prediction result and the collaborative potential analysis result, and generate a supply and demand gap matrix;

[0062] Step S400. Based on the energy flow correlation graph, in combination with the supply and demand gap matrix, the optimal scheduling path matched with the energy shortage grid is screened out from the energy surplus grid; according to the optimal scheduling path, a scheduling instruction is sent to the corresponding energy equipment, and the energy flow correlation graph is updated synchronously.

[0063] Step S100 comprises:

[0064] S101. Collect geographical information data and energy node information of a target region by using a cloud platform, wherein the target region is a spatial range for energy hosting and collaborative management, and the energy node is a physical entity in the target region with energy production, storage, conversion or consumption functions; according to the geographical information data and the energy node information, an area A_total of the target region and a distribution position of the energy node are obtained, the target region is equally divided into N_grid regional unit grids according to a preset area A_grid of the regional unit grid, N_grid=A_total / A_grid, and each divided regional unit grid is marked with a unique number g(m, n), wherein m∈[1, M], n∈[1, N], m represents a row number of the regional unit grid, n represents a column of the regional unit grid, M represents a horizontal grid number of the regional unit grid, and N represents a vertical grid number of the regional unit grid; and the geometric range of each regional unit grid is: a horizontal coordinate interval x∈[x_min+(m-1)·l_grid, x_min+m·l_grid], and a vertical coordinate interval y∈[y_min+(m-1)·l_grid, y_min+m·l_grid], wherein l_grid represents a side length of the regional unit grid, and the regional unit grid is a square; for any energy node i, the corresponding coordinates are represented as (xi, yi), and the corresponding grid number is g(mi, ni): mi∈[1, M], ni∈[1, N], thereby forming a mapping relationship between the energy node i and the corresponding regional unit grid number g(mi, ni);

[0065] S102. Obtain an energy node topology structure of the target region, obtain a mutual relationship between the energy nodes in the target region, and thereby construct a cross-grid energy flow correlation graph G=(V, E), wherein V represents a set of energy nodes of the target region, E represents a set of edges of the energy nodes of the target region, and an edge eij represents an energy transmission path of edge nodes i to j.

[0066] In this embodiment, it is assumed that the area of the target region is 10 square kilometers, and the geographical information data (including the minimum longitude and latitude coordinates (x_min, y_min)) and the energy node information (for example, the coordinates (xi, yi) of the power plant, the function of each energy node, the storage and consumption capacity, etc.) of the target region are collected by the cloud platform, the total area of the target region is A_total=10 km 2 ; it is assumed that the area of each regional unit grid is A_grid=0.25 km 2According to the formula N_grid = A_total / A_grid = 40, a total of 40 regional unit grids are needed; according to this division, the target region is equally divided into M rows and N columns of grids, assuming that the region is divided into 8 rows and 5 columns of grids (M = 8, N = 5), and the side length of each grid is l_grid = 0.5 km; each regional unit grid has a unique number g(m, n), where m represents the row number and n represents the column number; assuming that the coordinates of a power plant are (2.2 km, 3.1 km), then the grid number to which it belongs is (m, n) = (5, 4), that is, the power plant is located in the fifth row and fourth column grid.

[0067] Assuming that the set of energy nodes is V = {V1, V2,..., VN}, where each Vi represents an energy node (such as a power plant, a substation, etc.); the connection relationship between each node is represented by edge eij, where eij represents the energy transmission path between node i and node j. For cross-grid energy flow, the energy transmission path between different grids can be represented by setting edge eij. For example, if there is an energy transmission channel between the power plant in grid g(m1, n1) and the substation in grid g(m2, n2), then an edge e(m1, n1)→e(m2, n2) is formed in the graph.

[0068] Step S200 includes:

[0069] S201. Obtain the multi-energy historical data of each regional unit grid, wherein the multi-energy historical data includes power, heat and gas production, storage and consumption data; data alignment and standardization are performed on the multi-energy historical data of each regional unit grid, and time series D g(m,n) (t) is arranged, where t represents time, D g(m,n) (t) represents the multi-energy historical data of regional unit grid g(m, n) at time t, and D g(m,n) (t) = [P prod (m, n, t), S stor (m, n, t), E cons (m, n, t)], where P prod (m, n, t) represents the production data of regional unit grid g(m, n) at time t, S stor (m, n, t) represents the storage data of regional unit grid g(m, n) at time t, and E cons (m, n, t) represents the consumption data of regional unit grid g(m, n) at time t; based on the energy flow correlation graph, for any edge eij E E, for energy node i g(m1, n1) and energy node j g(m2, n2), the corresponding cross-grid transmission amount P trans (i→j, t) must satisfy the constraint condition: P trans(i→j, t)≤ Cap(eij) and P trans (i→j, t)≤ [P prod (m1, n1, t) + S stor_out (m1, n1, t)] - E cons (m1, n1, t)], where Cap(eij) represents the transmission path rated capacity of energy node i to energy node j, S stor_out represents the storage device output of the regional unit grid; for each regional unit grid g(m, n), the energy conservation in the grid must be satisfied, and the formula is:

[0070] P prod (m, n, t) +∑ in P trans (→g, t) + S stor_out (m, n, t) = E cons (m, n, t) +∑ out P trans (g→, t) + S stor_in

[0071] (m, n, t) + Δ loss (m, n, t), where∑ in P trans (→g, t) represents the total energy transmitted to the current regional unit grid by other regional unit grids,∑ out P trans (g→, t) represents the total energy transmitted to other regional unit grids by the current regional unit grid; S stor_in (m, n, t) represents the input of the storage device of the current regional unit grid; Δ loss (m, n, t) represents the energy loss in the current regional unit grid; the multi-energy historical data satisfying the constraint condition and the energy conservation in the grid is screened to form the historical effective data D valid_g(m,n) (t);

[0072] S202. Based on the transmission path eij existing in the energy flow correlation diagram, the energy instantaneous conversion efficiency η valid_g(m,n) (i→j, t) is calculated in combination with the effective data D trans (t), and η trans (i→j, t) = [P recv (j, t) / P trans (i→j, t)] x 100%, where P recv (j, t) represents the actual received energy of energy node j; according to the energy instantaneous conversion efficiency η trans (i→j, t), the average value in the corresponding time window is calculated, and the cross-grid average conversion efficiency ημ trans(i→j); based on the historical effective data D of each regional unit grid valid_g(m,n) (t), from which the corresponding time correlation features are extracted, for any two regional unit grids g(m1, n1) and g(m2, n2), the Pearson correlation coefficient is used to calculate the correlation coefficient p(g1, g2) of the corresponding time correlation features, and the time correlation features with the correlation coefficient p(g1, g2) greater than the threshold value p0 are screened out; according to the cross-grid average conversion efficiency ημ trans (i→j) and the correlation coefficient p(g1, g2) of the screened time correlation features, the comprehensive evaluation index C(g1, g2) = w1 x p(g1, g2) + w2 x ημ trans (i→j) is calculated, where w1 and w2 represent weight factors, and w1 + w2 = 1; the comprehensive evaluation indexes of all regional unit grids are summarized in the order of the regional unit grid numbers, thereby constructing the coupling feature matrix C, and the diagonal elements in the coupling feature matrix C are 1.

[0073] Step S300 includes:

[0074] S301. For each regional unit grid g(m, n), according to the corresponding historical effective data D valid_g(m,n) (t) and the coupling feature matrix C, the trained time series model is used to predict the multi-energy load of each regional unit grid, and the corresponding prediction formula is: (m,n) D' valid_g(m,n) (t+1) = f(D (m,n) (t)), where D' prod (t+1) represents the multi-energy prediction load at the next time point, and f() represents the prediction function obtained by the time series model; the multi-energy prediction load of each regional unit grid is obtained, and the energy net output ΔE(m, n, t) in the prediction period is calculated, and the calculation formula is:

[0075] ΔE(m, n, t) = P' stor_out (m, n, t) + S' cons (m, n, t) - E' h1 (m, n, t); according to the energy net output ΔE(m, n, t) in the prediction period, the surplus grid set H1 and the shortage grid set H2 are obtained, where H1 = {g(m, n) | ΔE(m, n, t) > E1}, H2 = {g(m, n) | ΔE(m, n, t) < -E2}, and E1 and E2 represent preset threshold values, which are set according to the target area energy supply and demand fluctuation characteristics;

[0076] S302. Based on the energy flow correlation graph, the surplus grid g h1 ∈H1 and the shortage grid g h2∈H2 transmission path eij, evaluate the feasibility of the energy conversion path, and define the corresponding evaluation index F(g h1 ,g h2 ), if the surplus grid g h1 and shortage grid g h2 There is a transmission path eij∈E and η trans (g h1 →g h2 )≥η min , then the evaluation index F(g h1 ,g h2 )=1; otherwise, the evaluation index F(g h1 ,g h2 )=0;where η trans (g h1 →g h2 ) represents the transition from surplus grid to shortage grid g h2 The average energy conversion efficiency, η min is the preset minimum efficiency threshold; based on the prediction results and the evaluation results of the feasibility of cross-energy conversion, the synergy potential matrix T is constructed, and the corresponding elements are defined as T(g h1 ,g h2 )=F(g h1 ,g h2 )×min(ΔE(g h1 ),|ΔE(g h2 )|)×η trans (g h1 →g h2 );

[0077] S303. For each regional unit grid g(m,n), calculate the initial gap Q0(m,n) without considering coordination, and Q0(m,n)=E' cons (m,n)-[P' prod (m,n,t)+S' stor_out (m,n,t)], where Q0(m,n) greater than 0 indicates a shortage, and Q0(m,n) less than 0 indicates a surplus. Based on the synergy potential matrix T, the surplus is allocated using a greedy algorithm: Q(m,n) = Q0(m,n)-∑ gh1∈H1 α(g h1 ,m,n)·T(g h1 ,m,n), where α(g h1 ,m,n) represents the distribution coefficient, the value range is [0,1], and ∑ gh1∈H1 α(g h1,m,n) is less than or equal to 1; when Q(m,n)>0, it indicates the energy shortage that still exists after coordinated scheduling; when Q(m,n)<0, it indicates the remaining energy surplus after coordinated scheduling; when Q(m,n)=0, it indicates that the energy supply and demand are completely balanced; all regional unit grids with Q(m,n)>0 are summarized as the final supply and demand gap, and are arranged in order of row number m and column number n of the grid number to construct the supply and demand gap matrix Q.

[0078] In this embodiment, the specific process of greedy allocation is as follows:

[0079] For the shortage grid H2, sort it by the absolute value of the initial gap |Q0(m,n)| from large to small (grids with larger gaps are prioritized), and for the surplus grid H1, sort it by the synergy potential matrix element T(g h1 ,g h2 ) Sort by size (prioritize the surplus resources with higher potential); start from the first shortage grid after sorting, and match the sorted surplus grids in turn: for the current shortage grid g(m,n), calculate its remaining gap R = |Q0(m,n)|-∑ 已分配 α·T, select the first unallocated surplus grid g h1 Calculate the corresponding allocation amount Alloc=min(R,T(g h1 ,m,n)·(1-∑ 已分配给其他网格 α(gh1,))); determine the distribution coefficient α(g h1 ,m,n)=Alloc / T(g h1 ,m,n), update the remaining gap R=R-Alloc; if the remaining gap R=0, turn to the next shortage grid; if the surplus grid g h1 When the sum of the allocation coefficients reaches 1, the next surplus grid is moved to. After the allocation is completed, the final supply and demand gap of each regional unit grid is: Q(m,n)=Q0(m,n)-∑ gh1∈H1 α(g h1 ,m,n)·T(g h1 ,m,n); when Q(m,n)<0, it indicates the remaining energy surplus after coordinated scheduling; when Q(m,n)=0, it indicates that the energy supply and demand are completely balanced; all regional unit grids with Q(m,n)>0 are summarized as the final supply and demand gap, and are arranged in order of row number m and column number n of the grid number to construct the supply and demand gap matrix Q.

[0080] Step S400 includes:

[0081] S401. Based on the energy flow correlation diagram and the supply-demand gap matrix Q, for each shortage grid g h2 , search all surplus grids g h1The feasible transmission path of P is: the transmission path eij∈E, and P trans (i→j,t)≤Cap(eij); surplus grid g h1 The dispatchable quantity must satisfy: P sched (g h1 ,t)≤|Q(g h1 )∣·β(g h1 ,g h2 ), where β(g h1 ,g h2 ) represents the distribution coefficient, the shortage grid g h2 The demand must satisfy P recv (g h2 ,t)≤Q(g h2 ), with the optimization goal of minimizing the total transmission loss and maximizing the conversion efficiency, the path comprehensive score S(e ij ), and S(eij)=w3·η trans (i→j)-w4·ΔL(e ij ), where η trans (i→j) represents the average conversion efficiency of the path, ΔL(e ij ) represents the path transmission loss, w3 and w4 represent weight factors, and w3+w4=1; according to the path comprehensive score S(e ij ) Arrange them in descending order to obtain candidate scheduling paths;

[0082] S402. For each shortage grid, prioritize matching the conversion efficiency (g h1 →g h2 )≥η min If there are multiple candidate scheduling paths, the path with the comprehensive score S(e ij )The largest candidate scheduling path is used as the matching optimal scheduling path, and the remaining amount of the surplus grid after scheduling is ensured to be Q(g h1 )-P sched (g h1 ,t)≥0, and the demand quantity Q(g h2 )-P recv (g h2 ,t)≤0; summarize the optimal scheduling paths of all shortage grids, generate scheduling instructions for energy equipment, and synchronously update the energy flow association diagram according to the actual scheduling results.

[0083] It is to be noted that, in the present text, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0084] Finally, it should be noted that the above-mentioned only constitutes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications, equivalent replacements, improvements and the like of the technical solutions described in the foregoing embodiments can still be made. Any modifications, equivalent replacements, improvements and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A regional energy hosting collaborative management method based on a cloud platform, characterized by: The method comprises the following steps: Step S100: Utilize the cloud platform to collect geographic information data and energy node information of the target area, divide the target area into several regional unit grids based on the geographic information data and energy node information, obtain the energy node topology of the target area, and construct a cross-grid energy flow association diagram; Step S200: Obtain multi-energy historical data for each regional unit grid, perform data rationality verification on the multi-energy historical data in conjunction with the energy flow correlation diagram, and filter the multi-energy historical data based on the verification results; calculate cross-grid energy conversion efficiency based on the energy flow correlation diagram and the filtered multi-energy historical data, and extract time correlation features to construct a coupling feature matrix; Step S300: Based on the energy flow correlation diagram and coupling characteristic matrix, the multi-energy load of each regional unit grid is predicted. Based on the energy flow correlation diagram, energy surplus grids are searched and the feasibility of cross-energy conversion is evaluated to conduct synergy potential analysis. Based on the prediction results and synergy potential analysis results, the energy supply and demand gap of each regional unit grid is calculated and a supply and demand gap matrix is ​​generated. Step S400. Based on the energy flow association diagram and the supply-demand gap matrix, the optimal scheduling path that matches the energy shortage grid is screened out from the energy surplus grid; according to the optimal scheduling path, a scheduling instruction is sent to the corresponding energy equipment, and the energy flow association diagram is updated synchronously.

2. The cloud platform-based regional energy hosting collaborative management method according to claim 1, characterized in that: The step S100 includes: S101. Utilize the cloud platform to collect geographic information data and energy node information of the target area. Based on the geographic information data and energy node information, obtain the area A_total of the target area and the distribution locations of the energy nodes. Divide the target area into N_grid regional unit grids according to the preset regional unit grid area A_grid, where N_grid = A_total / A_grid. Each divided regional unit grid is uniquely numbered g(m,n), where m∈[1,M] and n∈[1,N], where m represents the row number of the regional unit grid, n represents the column number of the regional unit grid, M represents the number of horizontal grid cells in the regional unit grid, and N represents the number of vertical grid cells in the regional unit grid. Furthermore, the geometric range of each regional unit grid is: The horizontal coordinate interval x∈[x_min+(m-1)·l_grid,x_min+m·l_grid], the vertical coordinate interval y∈[y_min+(m-1)·l_grid,y_min+m·l_grid], where l_grid represents the side length of the regional unit grid, and the regional unit grid is square; for any energy node i, the corresponding coordinate is expressed as (xi,yi), and the corresponding grid number is: And mi∈[1,M], ni∈[1,N], thus forming a mapping relationship between energy node i and the corresponding regional unit grid number g(mi,ni); S102. Obtain the energy node topology structure of the target area and obtain the mutual relationship between the energy nodes in the target area, so as to construct a cross-grid energy flow association graph G = (V, E), where V represents the energy node set of the target area, E represents the edge set of the energy nodes in the target area, and the edge eij represents the energy transmission path from edge node i to j.

3. The cloud platform-based regional energy hosting collaborative management method according to claim 2, characterized in that: The step S200 includes: S201. Obtain the multi-energy historical data of each regional unit grid, where the multi-energy historical data includes the production, storage, and consumption data of electricity, heat, and gas; align and standardize the multi-energy historical data of each regional unit grid and organize them into time series D g(m,n) (t), where t represents time, D g(m,n) (t) represents the multi-energy historical data of the regional unit grid g(m,n) at time t, and D g(m,n) (t)=[P prod (m,n,t),S stor (m,n,t),E cons (m,n,t)], where P prod (m,n,t) represents the production data of the regional unit grid g(m,n) at time t, S stor (m,n,t) represents the storage data of the regional unit grid g(m,n) at time t, E cons (m,n,t) represents the consumption data of the regional unit grid g(m,n) at time t; based on the energy flow association graph, for any edge eij∈E, for energy node i∈g(m1,n1) and energy node j∈g(m2,n2), the corresponding cross-grid transmission volume P trans (i→j,t) must satisfy the constraints: P trans (i→j,t)≤Cap(eij), and P trans (i→j,t)≤[P prod (m1,n1,t)+S stor_out (m1,n1,t)]-E cons (m1,n1,t)], where Cap(eij) represents the rated capacity of the transmission path from energy node i to energy node j, S stor_out Represents the storage device output of the regional unit grid; for each regional unit grid g(m,n), the energy conservation in the grid must be satisfied, and the formula is: P prod (m,n,t)+∑ in P trans (→g,t)+S stor_out (m,n,t)=E cons (m,n,t)+∑ out P trans (g→,t)+S stor_in (m,n,t)+Δ loss (m,n,t), where ∑ in P trans (→g,t) represents the total energy transmitted from other regional unit grids to the current regional unit grid, ∑ out P trans (g→,t) represents the total energy transferred from the current regional unit grid to other regional unit grids; S stor_in (m,n,t) represents the input amount of the grid storage device of the current area unit; Δ loss (m,n,t) represents the energy loss in the current regional unit grid; multiple energy historical data that meet the constraints and energy conservation in the grid are screened to form historical valid data D valid_g(m,n) (t); S202. Based on the transmission path eij in the energy flow association diagram, combined with the effective data D valid_g(m,n) (t), calculate the instantaneous energy conversion efficiency η trans (i→j,t), and η trans (i→j,t)=[P recv (j,t) / P trans (i→j,t)]×100%, where P recv (j, t) represents the actual received energy of energy node j; according to the energy instantaneous conversion efficiency η trans (i→j,t), calculate the average value in the corresponding time window, and thus get the average conversion efficiency ημ across the grid trans (i→j); based on the historical effective data D of each regional unit grid valid_g(m,n) (t), extract the corresponding time correlation features from it, for any two regional unit grids g(m1,n1) and regional unit grids g(m2,n2), use the Pearson correlation coefficient to calculate the correlation coefficient ρ(g1,g2) of the corresponding time correlation features, and screen the time correlation features with the correlation coefficient ρ(g1,g2) greater than the threshold ρ0; according to the cross-grid average conversion efficiency ημ trans The correlation coefficient ρ(g1, g2) between (i→j) and the filtered time correlation feature is used to calculate the comprehensive evaluation index C(g1, g2) = w1×ρ(g1, g2) + w2×ημ trans (i→j), where w1 and w2 represent weight factors, and w1+w2=1; the comprehensive evaluation indicators of all regional unit grids are summarized, and the coupling characteristic matrix C is constructed according to the numbering order of the regional unit grids, and the diagonal elements in the coupling characteristic matrix C are 1.

4. The cloud platform-based regional energy hosting collaborative management method according to claim 3, characterized in that: The step S300 includes: S301. For each regional unit grid g(m,n), according to the corresponding historical valid data D valid_g(m,n) (t) and the coupling feature matrix C, the trained time series model is used to predict the multi-energy load of each regional unit grid. The corresponding prediction formula is: D' (m,n) (t+1)=f(D valid_g(m,n) (t)), where D' (m,n) (t+1) represents the multi-energy predicted load at the next time point, and f() represents the prediction function obtained by the time series model. The multi-energy predicted load of each regional unit grid is obtained, and the net energy output ΔE(m,n,t) during the prediction period is calculated using the following formula: ΔE(m,n,t)=P' prod (m,n,t)+S' stor_out (m,n,t)]-E' cons (m,n,t); according to the net energy output ΔE(m,n,t) in the forecast period, the surplus grid set H1 and the shortage grid set H2 are obtained, where the surplus grid set H1 = {g(m,n)|ΔE(m,n,t)>E1}, and the shortage grid set H2 = {g(m,n)|ΔE(m,n,t)<-E2}, where E1 and E2 represent preset thresholds; S302. Analyze surplus grid g based on energy flow correlation diagram h1 ∈H1 and the shortage grid g h2 ∈H2 transmission path eij, evaluate the feasibility of the energy conversion path, and define the corresponding evaluation index F(g h1 ,g h2 ), if the surplus grid g h1 and shortage grid g h2 There is a transmission path eij∈E and η trans (g h1 →g h2 )≥η min , then the evaluation index F(g h1 ,g h2 )=1; otherwise, the evaluation index F(g h1 ,g h2 )=0;where η trans (g h1 →g h2 ) represents the transition from surplus grid to shortage grid g h2 The average energy conversion efficiency, η min is the preset minimum efficiency threshold; based on the prediction results and the evaluation results of the feasibility of cross-energy conversion, the synergy potential matrix T is constructed, and the corresponding elements are defined as T(g h1 ,g h2 )=F(g h1 ,g h2 )×min(ΔE(g h1 ),|ΔE(g h2 )|)×η trans (g h1 →g h2 ); S303. For each regional unit grid g(m,n), calculate the initial gap Q0(m,n) without considering coordination, and Q0(m,n)=E' cons (m,n)-[P' prod (m,n,t)+S' stor_out (m,n,t)], where Q0(m,n) greater than 0 indicates a shortage, and Q0(m,n) less than 0 indicates a surplus. Based on the synergy potential matrix T, the surplus is allocated using a greedy algorithm: Q(m,n) = Q0(m,n)-∑ gh1∈H1 α(g h1 ,m,n)·T(g h1 ,m,n), where α(g h1 ,m,n) represents the distribution coefficient, the value range is [0,1], and ∑ gh1∈H1 α(g h1 ,m,n) is less than or equal to 1; when Q(m,n)>0, it indicates the energy shortage that still exists after coordinated scheduling; when Q(m,n)<0, it indicates the remaining energy surplus after coordinated scheduling; when Q(m,n)=0, it indicates that the energy supply and demand are completely balanced; all regional unit grids with Q(m,n)>0 are summarized as the final supply and demand gap, and are arranged in order of row number m and column number n of the grid number to construct the supply and demand gap matrix Q.

5. The cloud platform-based regional energy hosting collaborative management method according to claim 4, characterized in that: The step S400 includes: S401. Based on the energy flow correlation diagram and the supply-demand gap matrix Q, for each shortage grid g h2 , search all surplus grids g h1 The feasible transmission path of P is: the transmission path eij∈E, and P trans (i→j,t)≤Cap(eij); surplus grid g h1 The dispatchable quantity must satisfy: P sched (g h1 ,t)≤|Q(g h1 )∣·β(g h1 ,g h2 ), where β(g h1 ,g h2 ) represents the distribution coefficient, the shortage grid g h2 The demand must satisfy P recv (g h2 ,t)≤Q(g h2 ), with the optimization goal of minimizing the total transmission loss and maximizing the conversion efficiency, the path comprehensive score S(e ij ), and S(eij)=w3·η trans (i→j)-w4·ΔL(e ij ), where η trans (i→j) represents the average conversion efficiency of the path, ΔL(e ij ) represents the path transmission loss, w3 and w4 represent weight factors, and w3+w4=1; according to the path comprehensive score S(e ij ) Arrange them in descending order to obtain candidate scheduling paths; S402. For each shortage grid, prioritize matching the conversion efficiency (g h1 →g h2 )≥η min If there are multiple candidate scheduling paths, the path with the comprehensive score S(e ij )The largest candidate scheduling path is used as the matching optimal scheduling path, and the remaining amount of the surplus grid after scheduling is ensured to be Q(g h1 )-P sched (g h1 ,t)≥0, and the demand quantity Q(g h2 )-P recv (g h2 ,t)≤0; summarize the optimal scheduling paths of all shortage grids, generate scheduling instructions for energy equipment, and synchronously update the energy flow association diagram according to the actual scheduling results.

6. A cloud-based regional energy hosting and collaborative management system, applied to a cloud-based regional energy hosting and collaborative management method according to any one of claims 1 to 5, characterized in that: The system includes: a regional grid division and correlation analysis module, a data verification and feature extraction module, a load forecasting and coordination potential analysis module, and a scheduling path optimization and instruction execution module; The regional grid division and association analysis module uses the cloud platform to collect geographic information data and energy node information of the target area, divides the target area according to the geographic information data and energy node information, thereby obtaining a number of regional unit grids; obtains the energy node topology structure of the target area, and thus constructs a cross-grid energy flow association diagram; The data verification and feature extraction module obtains the multi-energy historical data of each regional unit grid, performs data rationality verification on the multi-energy historical data in combination with the energy flow correlation diagram, and filters the multi-energy historical data based on the verification results; calculates the cross-grid energy conversion efficiency based on the energy flow correlation diagram and the filtered multi-energy historical data, and extracts time correlation features to construct a coupling feature matrix; The load forecasting and synergy potential analysis module predicts the multi-energy load of each regional unit grid based on the energy flow correlation diagram and the coupling characteristic matrix. Based on the energy flow correlation diagram, it searches for energy surplus grids and evaluates the feasibility of cross-energy conversion to conduct synergy potential analysis. Based on the forecast results and synergy potential analysis results, it calculates the energy supply and demand gap of each regional unit grid and generates a supply and demand gap matrix. The scheduling path optimization and instruction execution module is based on the energy flow association diagram and combined with the supply and demand gap matrix to screen out the optimal scheduling path that matches the energy shortage grid from the energy surplus grid; according to the optimal scheduling path, the scheduling instruction is sent to the corresponding energy equipment and the energy flow association diagram is updated synchronously.

7. The cloud platform-based regional energy hosting and collaborative management system according to claim 6, characterized in that: The regional grid division and association analysis module includes a grid division unit and an association graph construction unit; The grid division unit uses the cloud platform to collect geographic information data and energy node information of the target area, and divides the target area according to the geographic information data and energy node information to obtain a number of regional unit grids; the association graph construction unit obtains the energy node topological structure of the target area, thereby constructing an energy flow association graph across grids.

8. The cloud platform-based regional energy hosting and collaborative management system according to claim 6, characterized in that: The data verification and feature extraction module includes a data verification and screening unit and a coupling feature extraction unit; The data verification and screening unit obtains the multi-energy historical data of each regional unit grid, performs data rationality verification on the multi-energy historical data in combination with the energy flow association diagram, and screens the multi-energy historical data based on the verification results; the coupling feature extraction unit calculates the cross-grid energy conversion efficiency based on the energy flow association diagram and the screened multi-energy historical data, and extracts time correlation features, thereby constructing a coupling feature matrix.

9. The cloud platform-based regional energy hosting and collaborative management system according to claim 6, characterized in that: The load forecasting and synergy potential analysis module includes a multi-energy load forecasting unit and a synergy potential assessment and gap calculation unit; The multi-energy load prediction unit predicts the multi-energy load of each regional unit grid based on the energy flow association diagram and the coupling characteristic matrix; The synergy potential assessment and gap calculation unit searches for energy surplus grids and evaluates the feasibility of cross-energy conversion based on the energy flow association diagram, thereby performing synergy potential analysis; based on the prediction results and synergy potential analysis results, the energy supply and demand gap of each regional unit grid is calculated, and a supply and demand gap matrix is ​​generated.

10. The cloud platform-based regional energy hosting and collaborative management system according to claim 6, characterized in that: The scheduling path optimization and instruction execution module includes an optimal scheduling path screening unit and a scheduling instruction generation and association graph updating unit; The optimal scheduling path screening unit selects the optimal scheduling path that matches the energy shortage grid from the energy surplus grid based on the energy flow association diagram and combined with the supply and demand gap matrix; the scheduling instruction generation and association diagram updating unit sends scheduling instructions to the corresponding energy equipment according to the optimal scheduling path and synchronously updates the energy flow association diagram.

Images